{"id":"https://openalex.org/W4405623183","doi":"https://doi.org/10.1145/3698832","title":"Pasta: A Cost-Based Optimizer for Generating Pipelining Schedules for Dataflow DAGs","display_name":"Pasta: A Cost-Based Optimizer for Generating Pipelining Schedules for Dataflow DAGs","publication_year":2024,"publication_date":"2024-12-18","ids":{"openalex":"https://openalex.org/W4405623183","doi":"https://doi.org/10.1145/3698832"},"language":"en","primary_location":{"id":"doi:10.1145/3698832","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3698832","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3698832","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008766717","display_name":"Xiaozhen Liu","orcid":"https://orcid.org/0009-0006-5346-7028"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaozhen Liu","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0009-0006-5346-7028","affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034443538","display_name":"Yicong Huang","orcid":"https://orcid.org/0000-0002-1186-4803"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yicong Huang","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1186-4803","affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104329412","display_name":"Xinyuan Lin","orcid":"https://orcid.org/0000-0001-7935-0035"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyuan Lin","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7935-0035","affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102024672","display_name":"Avinash Kumar","orcid":"https://orcid.org/0009-0006-9327-3906"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avinash Kumar","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0009-0006-9327-3906","affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037388258","display_name":"Sadeem Alsudais","orcid":"https://orcid.org/0000-0003-3928-690X"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Sadeem Alsudais","raw_affiliation_strings":["King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-3928-690X","affiliations":[{"raw_affiliation_string":"King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092519189","display_name":"Chen Li","orcid":"https://orcid.org/0000-0001-8015-6870"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8015-6870","affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79192775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"2","issue":"6","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.9047037363052368},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7259095907211304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6988281011581421},{"id":"https://openalex.org/keywords/software-pipelining","display_name":"Software pipelining","score":0.5464575886726379},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.33347398042678833},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.29730257391929626},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.08078375458717346}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9047037363052368},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7259095907211304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6988281011581421},{"id":"https://openalex.org/C188854837","wikidata":"https://www.wikidata.org/wiki/Q268469","display_name":"Software pipelining","level":3,"score":0.5464575886726379},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33347398042678833},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29730257391929626},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.08078375458717346}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3698832","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3698832","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3698832","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3698832","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G489982137","display_name":"III: Medium: Collaborative Research: Collaborative Machine-Learning-Centric Data Analytics at Scale","funder_award_id":"2107150","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337357","display_name":"National Institute of Diabetes and Digestive and Kidney Diseases","ror":"https://ror.org/00adh9b73"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1969937393","https://openalex.org/W2034408574","https://openalex.org/W2083541728","https://openalex.org/W2105947650","https://openalex.org/W2199153319","https://openalex.org/W2547386789","https://openalex.org/W2971181729","https://openalex.org/W3008519452","https://openalex.org/W3042416858","https://openalex.org/W3176472315","https://openalex.org/W4282570934","https://openalex.org/W4294904053","https://openalex.org/W4312991867","https://openalex.org/W4385270707","https://openalex.org/W4386768521","https://openalex.org/W4402042779"],"related_works":["https://openalex.org/W2389666628","https://openalex.org/W1998888015","https://openalex.org/W1603958403","https://openalex.org/W1976397984","https://openalex.org/W4232563190","https://openalex.org/W2083147443","https://openalex.org/W2034393996","https://openalex.org/W1816081266","https://openalex.org/W1567574506","https://openalex.org/W2071386317"],"abstract_inverted_index":{"Data":[0],"analytics":[1],"tasks":[2],"are":[3,64],"often":[4],"formulated":[5],"as":[6,10,111],"data":[7,71,98],"workflows":[8,27,188],"represented":[9],"directed":[11],"acyclic":[12],"graphs":[13],"(DAGs)":[14],"of":[15,20,48,53,88,94,122,156,162,170,183,195],"operators.":[16],"The":[17,143],"recent":[18],"trend":[19],"adopting":[21],"machine":[22],"learning":[23],"(ML)":[24],"techniques":[25,185],"in":[26,29,66,166],"results":[28,55,61],"increasingly":[30],"complicated":[31],"DAGs":[32],"with":[33],"many":[34],"operators":[35,58,89],"and":[36,56,90,130,150,189,193],"edges.":[37],"Compared":[38],"to":[39,59,84,103,152,173],"the":[40,50,85,91,105,120,191],"operator-at-a-time":[41],"execution":[42,45,80],"paradigm,":[43],"pipelined":[44,79,128],"has":[46],"benefits":[47],"reducing":[49],"materialization":[51,112],"cost":[52,157,171],"intermediate":[54],"allowing":[57],"produce":[60],"early,":[62],"which":[63],"critical":[65],"iterative":[67],"analysis":[68],"on":[69,186],"large":[70],"volumes.":[72],"Correctly":[73],"scheduling":[74,123],"a":[75,124,132,140,153,167,180],"workflow":[76,125],"DAG":[77,126],"for":[78,127,138],"is":[81,146],"non-trivial":[82],"due":[83],"richer":[86],"semantics":[87],"increasing":[92],"complexity":[93],"DAGs.":[95],"Several":[96],"existing":[97],"systems":[99],"adopt":[100],"simple":[101],"heuristics":[102],"solve":[104],"problem":[106,121],"without":[107],"considering":[108],"costs":[109],"such":[110],"sizes.":[113],"In":[114],"this":[115],"paper,":[116],"we":[117],"systematically":[118],"study":[119],"execution,":[129],"develop":[131],"novel":[133],"cost-based":[134],"optimizer":[135,145],"called":[136],"Pasta":[137,144],"generating":[139],"high-quality":[141],"schedule.":[142],"not":[147],"only":[148],"general":[149],"applicable":[151],"wide":[154],"variety":[155],"functions,":[158],"but":[159],"also":[160],"capable":[161],"utilizing":[163],"properties":[164],"inherent":[165],"broad":[168],"class":[169],"functions":[172],"improve":[174],"its":[175],"performance":[176],"significantly.":[177],"We":[178],"conducted":[179],"thorough":[181],"evaluation":[182],"developed":[184],"real-world":[187],"show":[190],"efficiency":[192],"efficacy":[194],"these":[196],"solutions.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
